Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and their contexts pertaining to personal relationships or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     admittedly
    -0.72
     decidedly
    -0.69
    ̸
    -0.57
     Typically
    -0.54
     nécessairement
    -0.53
     réjou
    -0.53
     particularmente
    -0.52
     naturalmente
    -0.51
    voorbeeld
    -0.51
     typically
    -0.50
    POSITIVE LOGITS
     whole
    0.96
    orical
    0.88
     said
    0.88
    WriteLiteral
    0.81
     same
    0.81
     autorytatywna
    0.80
     mentioned
    0.78
     stuffs
    0.78
    styleType
    0.76
     ſame
    0.75
    Act Density 0.836%

    No Known Activations